"A Survey of Monte Carlo Tree Search Methods"


I will present Browne et al.'s "A Survey of Monte Carlo Tree Search Methods (http://citeseerx.ist.psu.edu/viewdoc/download;jsessionid=B7BB1338BDE1F287ECFC52AD86AFD055?doi=" along with some discussion of the application of MCTS to fuzzing, test generation, and procedural content generation. Some of these aspects can be seen as a followup or tangent to my presentation last year (http://www.meetup.com/Papers-We-Love-Montreal/events/217560332/) on shape grammars and procedural modeling of buildings.

MCTS has been enjoying a lot of interest for its success in playing Go, but it generally has a lot of applicability in search problems where coming up with good heuristics in advance is tricky.

The paper, being a survey paper, is pretty long; if you just want to get the general idea, read sections 2 and 3, which introduce MCTS, UCT, and the ideas leading up to them. (Including the minimization of regret; and who doesn't want to minimze regret?)

Be sure to check out http://mcts.ai for more MCTS reading.

AdGear have kindly offered to provide space this time. It's right next to metro Square Victoria. Note that the start time is a little earlier than usual; you can come at 6, and I'll try to speak starting around 6:30. As usual, we'll probably move to Pub Vic or a similar venue after the main discussion.

There will be code, beer, and pizza. As usual, if you get here early, you can browse some papers that I think are interesting. Feel free to bring your own collection to share!